Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    concepts related to legal presumption and innocence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uco
    -0.18
    ikut
    -0.14
     hope
    -0.14
     Bram
    -0.13
    zcze
    -0.13
    erald
    -0.13
    facet
    -0.13
    CppClass
    -0.13
    phere
    -0.13
    ugh
    -0.13
    POSITIVE LOGITS
    Defaults
    0.22
     defaults
    0.17
     Default
    0.16
     Defaults
    0.16
    	default
    0.16
    Default
    0.16
    _default
    0.16
     default
    0.16
    /default
    0.15
    ,default
    0.15
    Act Density 0.199%

    No Known Activations